What I’d do is set up a simple website that uses a little JavaScript to rewrite the date and time into the page and periodically refresh an image under/next to it. Size the image to fit the remaining free space of however you set up the iPad, and then you can stick anything you want there (pictures/reminder text/whatever) with your favorite image editor. Upload a new image to the server when you want to change the note. The idea with an image is that it’s just really easy to do and keeps the amount of effort to redo layout to a minimum – just drag stuff around in your image editor and you’ll know it’ll all fit as expected as long as you don’t change the resolution (instead of needing to muck around with CSS and maybe breaking something if you can’t see the device to check that it displays correctly).

There’s a couple issues to watch out for – e.g. what happens if the internet connection/server goes down, screen burn-in, keeping the browser from being closed/switched to another page, keeping it powered, etc. that might or might not matter depending on your particular circumstances. If you need to fix all that for your circumstances, it might be more trouble than just buying something purpose built… but getting a first pass DIY version working is trivial if you’re comfortable hosting a website.

Edit: If some sample code that you can use as a starting point would be helpful, let me know.

GPT4-Vision can do it, sort of. It doesn’t have a particularly great understanding of what’s going on in a scene, but it can be used for some interesting stuff. I posted a link a few weeks back to an example from DALL-E Party, which hooks up an image generator and an image describer in a loop: https://kbin.social/m/imageai@sh.itjust.works/t/661021/Paperclip-Maximizer-Dall-E-3-GPT4-Vision-loop-see-comment

merde posted a link in the comments there to the goatpocalypse example – https://dalle.party/?party=vCwYT8Em – which is even more fun.

I mean, we all know what happened when old Godzilla was hoppin’ around Tokyo city like a big playground… right?

I tried messing around with the colors a bit in an image editor and this was the best adaptation I could make: https://files.catbox.moe/03k8sc.png

Reminds me a bit of Kammy Koopa

Oh man, the goatpocalypse! That’s great.

This seems like it’s ripe for all sorts of fun twists.

Over on Hacker News, user z991 had the fun idea of hooking up Dall-E 3 and GPT4-Vision in a loop and they made a Show HN thread about it: https://news.ycombinator.com/item?id=38432486

This is the image output from part way through one of their results that I enjoyed. You can see the rest of the chain here: https://dalle.party/?party=RqpIijhH

Prompt – note, multiple parts! Initial prompt to Dall-E, another for GPT4 to generate prompts for Dall-E to make more images from, and one for what was fed to Dall-E later in the chain.

Original prompt to Dall-E:

A truck going down a highway at full speed

GPT4V Prompt:

Write a prompt for an AI to make this image. Just return the prompt, don’t say anything else. Replace everything with a paperclip.

Five steps deep in the chain, this is the prompt GPT4 generated:

Create an image of a surreal landscape where everything is made of paperclips. There should be winding roads, mountain ranges, and forests, with the sun setting in the background. The elements, including the trees, mountains, and roads, should all have a metallic paperclip texture and appearance. The overall scene should have a warm, golden hue to simulate sunset lighting.

There’s a lot of other fun combinations like “Corgi insanity” in the thread as well.

It was so startled the spaghetti landed on the cat’s head!

You’ve just reminded me of Bonkers. Man, I haven’t thought of that cartoon in years. This cat looks more serious though.

!cursed_ai might like this

Kind of reminds me of Berri from Conker’s Bad Fur Day (although this character isn’t blonde).